Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Diabetic Retinopathy01:27

Diabetic Retinopathy

55
DefinitionDiabetic retinopathy is a microvascular complication of diabetes affecting the retinal blood vessels.Risk FactorsDiabetic retinopathy is present in almost all individuals with type 1 diabetes and more than 60% of those with type 2 diabetes after two decades of disease.The risk increases with poor glycemic control, hypertension, dyslipidemia, smoking, pregnancy, and puberty.Although cataracts and glaucoma are also more frequent in people with diabetes, retinopathy remains the leading...
55

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A novel class-attention transformer-driven feature fusion technique-based speech disorder classification.

Frontiers in medicine·2026
Same author

AI-enabled eye-movement and emerging multimodal frameworks for precision dyslexia screening and reading pattern analysis.

Frontiers in medicine·2026
Same author

A hybrid optimized framework with energy shape prior segmentation for brain tumor detection in MRI images.

Digital health·2026
Same author

Digital twin-assisted blockchain IoT security model using contrastive and causal learning techniques.

Scientific reports·2026
Same author

Involvement of the PD-1 pathway in the modulation of immune responses during allergic diseases.

Inflammation research : official journal of the European Histamine Research Society ... [et al.]·2026
Same author

A Novel Hybrid CNN-ViT-Based Bi-Directional Cross-Guidance Fusion-Driven Breast Cancer Detection Model.

Life (Basel, Switzerland)·2026

Related Experiment Video

Updated: May 1, 2026

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
07:41

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats

Published on: October 23, 2020

7.1K

Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional

Ashit Kumar Dutta1,2, Nasser Ali Aljarallah1,2, Abdul Rahaman Wahab Sait2,3

  • 1Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University, Riyadh, Saudi Arabia.

Frontiers in Medicine
|March 30, 2026
PubMed
Summary

This study presents a deep learning model for grading diabetic retinopathy (DR) severity from retinal images. The model achieved 93.84% accuracy on the Messidor-2 dataset, offering efficient DR detection for clinical use.

Keywords:
Kolmogorov-Arnold networkShuffleNet V2diabetic retinopathyfundus imageshyperparameter optimizationimproved Whale optimizationpre-trained modelstransfer learning

More Related Videos

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability
07:23

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

3.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Related Experiment Videos

Last Updated: May 1, 2026

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
07:41

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats

Published on: October 23, 2020

7.1K
Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability
07:23

Optimization of the Retinal Vein Occlusion Mouse Model to Limit Variability

Published on: August 6, 2021

3.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Diabetic retinopathy (DR) is a leading cause of vision impairment globally, driven by uncontrolled blood glucose.
  • Current deep learning (DL) methods for DR detection require further improvement for early-stage diagnosis.
  • Accurate and timely DR grading is crucial for effective patient management and vision preservation.

Purpose of the Study:

  • To develop and validate a novel deep learning model for automated diabetic retinopathy severity grading using retinal fundus images.
  • To enhance the accuracy and efficiency of DR detection, aiding medical professionals in early diagnosis.
  • To create a computationally efficient model suitable for deployment in resource-limited healthcare settings.

Main Methods:

  • A hybrid DL approach combining ShuffleNet V2 with a vision transformer (ViT) attention mechanism for feature extraction.
  • An improved Whale optimization (IWO) algorithm was used for fine-tuning the feature extraction model.
  • A convolutional Kolmogorov-Arnold Network was employed for DR severity classification, trained on the EyePACS dataset with five-fold cross-validation and generalized on the Messidor-2 dataset.

Main Results:

  • The proposed model achieved an average accuracy of 93.84% on the independent Messidor-2 dataset.
  • Demonstrated significant improvement in detecting diabetic retinopathy severity from fundus images.
  • The model requires minimal processing resources, facilitating its implementation in diverse clinical environments.

Conclusions:

  • The developed DL model shows high accuracy and efficiency in grading diabetic retinopathy severity.
  • This approach offers a promising tool for early DR detection and management, especially in resource-constrained areas.
  • The model's low computational demands support its integration into routine clinical practice for improved patient outcomes.